Abstract
This work aims to evaluate the efficiency of the five fundamental reinforcement learning algorithms including Q-learning, Sarsa, Watkins’s Q(λ), Sarsa(λ), and Dyna-Q, and indicate which one is the most efficient of the five algorithms for the path planning problem of autonomous mobile robots. In the sense of the reinforcement learning algorithms, the Q-learning algorithm is the most popular and seems to be the most effective model-free algorithm for a learning robot. However, our experimental results show that the Dyna-Q algorithm, a method learns from the past model-learning and direct reinforcement learning is particularly efficient for this problem in a large environment of states.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Dudek G, Jenkin M (2010) Computational principles of mobile robotics. Cambridge University Press, New York
Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. J Artif Intell Res 4:237–285
Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. The MIT Press, Cambridge
Watkins C (1989) Learning from delayed rewards. Ph.D. Dissertation, King’s College
Smart WD, Kaelbling LP (2002) Effective reinforcement learning for mobile robots. In: IEEE international conference on robotics and automation (ICRA’02), vol 4. IEEE Press, Washington, pp 3404–3410
Zamstein L, Arroyo A, Schwartz E, Keen S, Sutton B, Gandhi G (2006) Koolio: path planning using reinforcement learning on a real robot platform. In: 19th Florida conference on recent advances in robotics, Florida
Chakraborty IG, Das PK, Konar A, Janarthanan R (2010) Extended Q-learning algorithm for path-planning of a mobile robot. In: LNCS, vol 6457. Springer, Heidelberg, pp 379–383
Mohammad AKJ, Mohammad AR, Lara Q (2011) Reinforcement based mobile robot navigation in dynamic environment. Robotics Comput-Integr Manuf 27:135–149
Acknowledgments
This research was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science, and Technology (2010-0012609).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media B.V.
About this paper
Cite this paper
Viet, H.H., Kyaw, P.H., Chung, T. (2011). Simulation-Based Evaluations of Reinforcement Learning Algorithms for Autonomous Mobile Robot Path Planning. In: Park, J., Arabnia, H., Chang, HB., Shon, T. (eds) IT Convergence and Services. Lecture Notes in Electrical Engineering, vol 107. Springer, Dordrecht. https://doi.org/10.1007/978-94-007-2598-0_49
Download citation
DOI: https://doi.org/10.1007/978-94-007-2598-0_49
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-007-2597-3
Online ISBN: 978-94-007-2598-0
eBook Packages: EngineeringEngineering (R0)